September 12, 2025SensorsOpen Access

High-Resolution Remote Sensing Imagery Water Body Extraction Using a U-Net with Cross-Layer Multi-Scale Attention Fusion

View Full Paper

Ask AI

Bookmark

Authors

CHChunyan HuangNorth University of China MWMingyang WangNational University of Singapore ZZZichao ZhuNorth China University of Water Resources and Electric Power

Discussion

Member takes

Implication

The proposed AMU-Net enhances water body extraction accuracy using innovative attention mechanisms, indicating significant improvement in segmentation performance.

Key Points

AMU-Net achieved IoU scores of 93.6% and 95.02% on GID and WHDLD datasets, respectively, illustrating superior extraction accuracy.
A dual-attention gated modulation module improved water boundary localization, enhancing the model's segmentation performance.
The model combines grouped channel attention with multi-scale convolution to address the challenges of previous CNN approaches.
A triple-constraint loss framework optimizes segmentation by focusing on global classification and regional overlap.

Cite This Study

Huang et al. (2025) studied this question.

synapsesocial.com/papers/68d41ed9713b0b5dfea67c08 https://doi.org/10.3390/s25185655

View Full Paper

Ask AI

Bookmark

Implication

The proposed AMU-Net enhances water body extraction accuracy using innovative attention mechanisms, indicating significant improvement in segmentation performance.

High-Resolution Remote Sensing Imagery Water Body Extraction Using a U-Net with Cross-Layer Multi-Scale Attention Fusion

Discussion

Member takes

Implication

Key Points

Cite This Study

High-Resolution Remote Sensing Imagery Water Body Extraction Using a U-Net with Cross-Layer Multi-Scale Attention Fusion

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider